arXiv:2103.14540
NL-EDIT: Correcting semantic parse errors through natural language interaction
원문 초록
We study semantic parsing in an interactive setting in which users correct errors with natural language feedback. We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to generate a sequence of edits that can be applied to the initial parse to correct its errors. We show that NL-EDIT can boost the accuracy of existing text-to-SQL parsers by up to 20% with only one turn of correction. We analyze the limitations of the model and discuss directions for improvement and evaluation. The code and datasets used in this paper are publicly available at http://aka.ms/NLEdit.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sigma: A dataset for text-to-code semantic parsing with statistical analysis
Disambiguate First Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing
SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition
Improving Generalization in Semantic Parsing by Increasing Natural Language Variation
Semantic Decomposition of Question and SQL for Text-to-SQL Parsing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.